Independent Standards
for the Agent Ecosystem
AI agents are becoming a primary interface between developers and the tools they use. We study how agents actually behave, publish open specifications based on what we find, and build the tools that measure compliance. 500+ sites already scored against our specs.
What We Do
Standards, Tools, Research, and Education
We study how agents interact with documentation, tools, and web infrastructure, then turn what we learn into open specs, compliance tooling, and practical guidance.
Standards
Open specifications that codify what actually matters for agent success into measurable, testable checks. Companies are already competing on their scores.
Tooling
Open-source tools like afdocs and skill-validator that let anyone measure their work against our specs. Automated scoring that turns standards into practice.
Research
Systematic study of how AI agents consume documentation, use tools, and interact with the broader ecosystem. Every finding is based on direct observation and published openly.
Education
Articles, talks, webinars, and resources that help practitioners understand what agents actually need and where the gaps are between assumption and reality.
Our Work
Published Research
and Standards
Concrete outputs from the Institute, freely available to the community.
Agent-Friendly Documentation Spec
A 22-check specification defining what makes documentation accessible to coding agents. Covers llms.txt, markdown availability, page size, content structure, URL stability, discoverability, and more. Built from empirical observation of agent behavior across hundreds of documentation sites.
Agent Skill Report
Qualitative analysis of 673+ public Agent Skills, including findings on spec compliance issues across the ecosystem. The first systematic evaluation of agent tool quality.
Automated Research Infrastructure
A four-stage daily pipeline: news-gather scans RSS, arXiv, and GitHub releases; research-sourcing evaluates items and tracks themes using vector search; shift-sourcing drafts and fact-checks commentary articles; and a dashboard synthesizes it all. New content generated daily and published on aeshift.com.
Explore ResearchDetailsThe Problem
Why This Work Matters
Ecosystem health directly affects product adoption. When infrastructure doesn’t work with agents, everyone loses.
The agent ecosystem is fragmented
Standards are being drafted. Best practices don’t exist yet. Most companies building in this space focus on model capabilities and leave the surrounding ecosystem to chance.
Documentation Failures
When docs don’t work with agents, developers blame the agent. We study these failure modes systematically.
Tool Quality Gaps
If tool integrations are unreliable, developers stop using them. We evaluate and report on tool quality.
Neutral ground for pre-competitive research
Standards and best practices benefit everyone, but no single company wants to fund them alone or be seen as controlling them
Sponsors help shape practical standards without the appearance of self-dealing, and associate their brand with credible independent work
Published findings reflect what the data shows, not what sponsors prefer. That independence is what makes the research useful
By the Numbers
Standards Already
Driving Change
Companies are measuring their documentation against our specs,
competing on their scores, and requesting to be listed.
22-Check Documentation Spec
A comprehensive specification defining what makes documentation accessible to coding agents, covering structure, discoverability, and content quality.
673+ Agent Skills Audited
The first systematic evaluation of public Agent Skills, revealing patterns in quality, compliance, and developer experience across the ecosystem.
8 Public Repositories
Specifications, validation tools, benchmarks, community research, and an enterprise variant, all publicly available under the agent-ecosystem GitHub organization. Backed by internal research infrastructure powering the daily pipeline.
Four-Stage Daily Pipeline
Automated news gathering, research evaluation, article drafting, and dashboard synthesis running daily on self-hosted infrastructure with MongoDB Atlas and vector search.
8 Live Sites
Including agentdocsspec.com for the spec, afdocs.dev for the scoring tool, aeshift.com for ecosystem commentary, agentreadingtest.com for agent benchmarking, and dedicated sites for published reports and community research.
Multiple Distribution Channels
Tools available via npm, Homebrew, Go install, and pre-commit hooks. Enterprise variant with AWS Bedrock integration for organizations with existing cloud infrastructure.
Sponsorship Tiers
Support the Institute
Every company building agent tooling, developer platforms, or AI-powered developer tools benefits from independent standards and a healthier agent ecosystem.
Sustaining Sponsor
Support ongoing research and standards work. Perfect for companies that benefit from a healthier agent ecosystem.
- Logo and attribution on all published reports and the Institute website
- Early access to research findings (2 weeks before public release)
- Quarterly briefings on research themes and emerging patterns
- Input on research direction and priorities
- Named acknowledgment in articles and presentations
- One custom analysis per quarter
Founding Sponsor
FoundingShape the Institute from its earliest days. For companies that want to lead in agent ecosystem standards.
- Everything in Sustaining, plus:
- Co-branded report option for one publication per year
- Direct access to raw research data and pipeline outputs
- Invitation to shape the research roadmap in annual planning
Help Build the Agent Ecosystem’s Infrastructure
The Institute is independent by design. Sponsors support our work; they don’t direct conclusions. That independence is what makes the standards and research credible and useful to the industry.
Become a Sponsor